Related Experiment Video For Alpha-fetoprotein
Updated: Jan 9, 2026
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
Integrating Contrast-Enhanced Ultrasound Features and Serum Biomarkers in an Online Tool Optimizes Noninvasive
Feihang Wang1, Yanni Chen1, Yadan Xu1
1Shanghai Institute of Medical Imaging, Shanghai, China; Department of Ultrasound, Zhongshan Hospital, Fudan University, Shanghai, China.
Objective:
To assess the diagnostic efficacy of the contrast-enhanced ultrasound (CEUS) features combined with serum tumor biomarkers for the diagnosis of hepatocellular carcinoma (HCC).
Methods:
This retrospective study included 1487 patients who underwent liver CEUS. The reference criteria included histopathological or comprehensive imaging and the clinical follow-up results. Clinical data, serum biomarkers and CEUS features were analyzed via logistic regression analysis to determine independent factors associated with HCC and a nomogram model was built. The diagnostic performance was evaluated in terms of sensitivity, specificity, accuracy, and area under the curve (AUC), and compared with different models.
Results:
The final model involved sex, age, AFP, DCP, APHE, and late wash-out. The nomogram demonstrated superior diagnostic accuracy for HCC with AUC: 0.934, 95% CI: 0.917-0.950; sensitivity: 0.868, 95% CI: 0.842-0.891; specificity: 0.895, 95% CI: 0.858-0.925) in the training cohort, and with an AUC of 0.929 (95% CI: 0.901-0.957), sensitivity of 0.872 (95% CI: 0.823-0.912), and specificity of 0.890 (95% CI: 0.827-0.936) in the validation cohort. Furthermore, for lesions with a maximum diameter ≤20 mm, the nomogram maintained robust diagnostic accuracy in the training cohort (AUC 0.888, 95% CI: 0.836-0.941; sensitivity 0.804, 95% CI: 0.733-0.863; specificity 0.870, 95% CI: 0.737-0.951), and in the validation cohort (AUC: 0.877, 95% CI: 0.789-0.965; sensitivity: 0.768, 95% CI: 0.636-0.870; specificity: 0.885, 95% CI: 0.698-0.976).
Conclusion:
CEUS features combined with the serum biomarkers accurately predicted the presence of HCC, achieving an optimal balance. With web-based and mobile calculators for easy use.
More Related Videos
05:56Evaluation of the Feasibility, Safety, and Accuracy of an Intraoperative High-intensity Focused Ultrasound Device for Treating Liver Metastases
Published on: January 9, 2019
06:09Author Spotlight: Advancing Hepatic Fibrosis Diagnosis Using Magnetic Resonance Elastography and AI
Published on: July 21, 2023
